INDEX

Explanations

terms related to features and highlights of subjects or items

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xaml

-0.74

olerance

-0.70

nesty

-0.68

RDA

-0.64

KEYCODE

-0.63

IBA

-0.63

keyCode

-0.62

 LEYENDO

-0.62

KTM

-0.62

transQ

-0.61

POSITIVE LOGITS

 featuring

1.43

featuring

1.36

 featured

1.34

Featuring

1.33

 Featuring

1.25

 features

1.11

 Featured

1.05

featured

1.04

Featured

1.02

 showcasing

1.02

Activations Density 0.101%

terms related to features and highlights of subjects or items

No Comments

No Known Activations